© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83341
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Norbert
    0.45
    Ｎ
    0.41
    𝑁
    0.41
     N
    0.41
     Anthony
    0.40
     Ν
    0.39
     Kann
    0.39
     Kart
    0.39
     Αν
    0.39
     Eileen
    0.39
    POSITIVE LOGITS
    日至
    0.38
    braio
    0.37
     dersimizde
    0.37
     czł
    0.36
    ほん
    0.35
    %)$
    0.35
    well
    0.35
    crew
    0.35
     welchem
    0.35
    ાઓ
    0.34
    Activations Density 0.000%

    No Known Activations